Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries about specific topics or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tanleria
    -1.11
     Efq
    -0.88
     Reſ
    -0.84
     reaſon
    -0.84
     reafon
    -0.84
     Majefty
    -0.84
     itſelf
    -0.82
     myſelf
    -0.82
     Diſ
    -0.81
     Normdatei
    -0.81
    POSITIVE LOGITS
     do
    0.56
     exactly
    0.52
     to
    0.51
    :
    0.51
     exatamente
    0.48
     
    0.47
     exactement
    0.47
     you
    0.47
     expect
    0.45
     does
    0.44
    Act Density 0.101%

    No Known Activations